chore: import upstream snapshot with attribution

libs/text-splitters/scripts/check_imports.py

@@ -0,0 +1,19 @@
+import sys
+import traceback
+import uuid
+from importlib.machinery import SourceFileLoader
+
+if __name__ == "__main__":
+    files = sys.argv[1:]
+    has_failure = False
+    for file in files:
+        try:
+            module_name = f"test_module_{uuid.uuid4().hex[:20]}"
+            SourceFileLoader(module_name, file).load_module()
+        except Exception:  # noqa: BLE001
+            has_failure = True
+            print(file)  # noqa: T201
+            traceback.print_exc()
+            print()  # noqa: T201
+
+    sys.exit(1 if has_failure else 0)

libs/text-splitters/scripts/lint_imports.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+set -eu
+
+# Initialize a variable to keep track of errors
+errors=0
+
+# make sure not importing from langchain or langchain_experimental
+# allow langchain.agents and langchain.tools (v1 middleware)
+git --no-pager grep "^from langchain\." . | grep -v ":from langchain\.agents" | grep -v ":from langchain\.tools" && errors=$((errors+1))
+git --no-pager grep "^from langchain_experimental\." . && errors=$((errors+1))
+
+# Decide on an exit status based on the errors
+if [ "$errors" -gt 0 ]; then
+    exit 1
+else
+    exit 0
+fi